Thread

1. mjg59 · 1790230761 · focus · HN ↗

   Hrm, something of a lack of discussion about what level of access the card has to the host in the absence of IOMMU-restricted passthrough.

   1. orphereus · 1790231063 · focus · HN ↗

      I am very sceptical about this. I have some experience in GPU virtualization and passthrough with Nvidia GPUs and they are really not designed to be able to share them with multiple guests/host without Nvidia's blessing (licenced drivers).

      1. WanjohiRyan · 1790231531 · focus · HN ↗

         Yes they are not... we run the Nvidia drivers unmodified. Only thing we have done is make the guest driver think it's running on the host, talking to the host's GPU kernel.

         It works really well with a ~2% performance penalty. Nvproxy by google/gvisor has been doing this for years.

         You should try running it yourself and see how it goes :D

         1. mjg59 · 1790232707 · focus · HN ↗

            Does "how it goes" include the guest being able to DMA over the host kernel?

            1. WanjohiRyan · 1790233901 · focus · HN ↗

               [dead]

Unofficial Hacker News client; not affiliated with Y Combinator.